Abstract: An investment portfolio is comprised of various assets with their own specific risk and return characteristics. The diversity of a portfolio facilitates the portfolio manager with a level of freedom to maintain it according to a preset target performance. Therefore, designing an optimal portfolio for the desired specification and its maintenance (rebalancing) in time require financial acumen along with expertise in econometrics and risk management. In order to estimate the risk of a portfolio with N assets defined in (3.3.7), we need to estimate N(N − 1)/2 cross-correlations of pairwise asset returns to form its N × N empirical correlation matrix, P(3.2.12). It is known that, P^ contains a significant amount of inherent measurement noise due to market microstructure that needs to be removed. Eigenfiltering has been successfully employed to filter out this undesirable noise component from the measured correlations [41, 55–57]. In this chapter, we discuss in detail the eigenfiltering of P^ for better risk estimation of a portfolio. We also introduce approximations to the correlation matrix for efficient noise filtering. Then, we revisit a straightforward risk management method and its two modifications. We conclude the chapter by demonstrating the performance improvements due to the modifications in the original method.
Publication Year: 2015
Publication Date: 2015-01-01
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot